视觉阵列处理器超越函数加速单元设计

doi:10.3969/j.issn.1001-2400.2018.04.029

Abstract

Abstract:

Computer vision algorithms involve a large number of transcendental function calculations. For accelerating the processing speed of the computer vision algorithm on a computer vision array processor and meeting the real time requirement of vision application, an algorithm of piece-wise linear approximation based on adjusting intercept is proposed, and a transcendental function calculator pipeline structure is designed based on the proposed algorithm, which employs a mixture operation system of the fixed-point number and the logarithmic number system. The function of cos/sin is computed approximately. Meanwhile, based on the logarithm/exponent convertor, the other functions are computed in the logarithmic number system. Simulation is done based on hundreds of random data and the architecture is synthesized using SMIC 0.13μm technology. The proposed structure improves the system throughput and reduces the computational error with the clock frequency reaching 200MHz.

Key words: computer vision array processor, transcendental function, fixed-point number system, logarithmic number system, pipeline

SHAN Rui;LI Tao;JIANG Lin;DENG Junyong;YANG Bowen;SHEN Xubang. Design of the transcendental function computing unit of the computer vision array processor[J].Journal of Xidian University, 2018, 45(4): 166-173.

References

［1］ ANIRUDH B K, VENKATRAMAN V, KUMAR A R, et al. Accelerating Real-time Computer Vision Applications Using HW/SW Co-design［C］//Proceedings of the 2017 International Conference on Computer, Communications and Electronics. Piscataway: IEEE, 2017: 458-463.
［2］ LEE Y, JANG C, KIM H. Accelerating a Computer Vision Algorithm on a Mobile SoC Using CPU-GPU Co-processing—a Case Study on Face Detection［C］//Proceedings of the 2016 International Conference on Mobile Software Engineering and Systems. Piscataway: IEEE, 2016: 70-76.
［3］ TAGLIAVINI G, HAUGOU G, MARONGIU A, et al. ADRENALINE: an OpenVX Environment to Optimize Embedded Vision Applications on Many-core Accelerators［C］//Proceedings of the 2015 IEEE 9th International Symposium on Embedded Multicore/Many SoCs. Piscataway: IEEE, 2015: 289-296
［4］陈云霁. 从人工智能到神经网络处理器［J］. 领导科学论坛, 2017(2): 38-55.
CHEN Yunji. From artificial Intelligence to Neural Network Processors［J］. The Forum of Leadership Science, 2017(2): 38-55.
［5］ HAMEED R, QADEER W, WACHS M, et al. Understanding Sources of Ineffciency in General-purpose Chips［J］. Communications of the ACM, 2011, 54(10): 85-93.
［6］ CHANG C H, CHEN S H, CHEN B W, et al. Fixed-point Computing Element Design for Transcendental Functions and Primary Operations in Speech Processing［J］. IEEE Transactions on Very Large Scale Integration Systems, 2016, 24(5): 1993-1997.
［7］ GUPTA S D, THORNTON M A. A Fixed-point Squaring Algorithm Using an Implicit Arbitrary Radix Number System［J］. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2016, 6(1): 34-43.
［8］ CHANG C H, CHEN S H, CHEN B W, et al. A Division-free Algorithm for Fixed-point Power Exponential Function in Embedded System［C］//Proceedings of the 2013 1st International Conference on Orange Technologies. Washington: IEEE Computer Society, 2013: 223-226.
［9］ RENARDY A P, AHMADI N, FADILA A A, et al. FPGA Implementation of CORDIC Algorithms for Sine and Cosine Generator［C］//Proceedings of the 2015 5th International Conference on Electrical Engineering and Informatics. Piscataway: IEEE, 2015: 1-6.
［10］ SINGH A K, SINGH M K, RAY K C. Design and Implementation of Quadruple Floating-point CORDIC［C］//Proceedings of the 2015 IEEE International Symposium on Nanoelectronic and Information Systems. Piscataway: IEEE, 2015: 286-290.
［11］ KAPGATE P S, GUGULOTHU S P. Design and Implementation of Complex Arithmetic Operations Using Binary Logarithmic Number System［C］//Proceedings of the 2015 International Conference on Communications and Signal Processing. Piscataway: IEEE, 2015: 1374-1377.
［12］ NAM B G, KIM H, YOO H J. Power and Area-efficient Unified Computation of Vector and Elementary Functions for Handheld 3D Graphics Systems［J］. IEEE Transactions on Computers, 2008, 57(4): 490-504.
［13］ NAM B G, YOO H J. An Embedded Stream Processor Core Based on Logarithmic Arithmetic for a Low-power 3-D Graphics SoC［J］. IEEE Journal of Solid-State Circuits, 2009, 44(5): 1554-1570.

[1]	CHEN Zhenhai, WEI Jinghe, YU Zongguang, SU Xiaobo, XUE Yan, ZHANG Hong. High precision common mode charge error fore-ground calibration circuit for the charge-domain ADC [J]. Journal of Xidian University, 2018, 45(6): 137-143+149.
[2]	CHEN Zhenhai;WEI Jinghe;SU Xiaobo;ZOU Jiaxuan;ZHANG Hong;YU Zongguang. Low power time-interleaved 12-bit 500MS／s charge-domain ADC [J]. Journal of Xidian University, 2017, 44(6): 109-115+137.
[3]	CHEN Zhenhai;YU Zongguang;LI Xiankun;WEI Jinghe;HUANG Songren;SU Xiaobo. High precision voltage reference generator for 16-bit 100MS/s ADC [J]. Journal of Xidian University, 2017, 44(3): 127-132+180.
[4]	HUANG Songren;CHEN Zhenhai;ZHANG Hong;LI Xue;QIAN Hongwen;YU Zongguang. 1.5bit substage circuit for charge domain pipelined ADCs [J]. Journal of Xidian University, 2016, 43(6): 170-175.
[5]	WANG Xiaofei;HAO Yue. Design of double sample 1.2V 7bit 125MS/s pipelined ADC [J]. Journal of Xidian University, 2016, 43(4): 23-28.
[6]	DONG Siwan;ZHU Zhangming;LIU Minjie;YANG Yintang. Optimum design of the MDAC circuit for the 8bit 80MS/s pipelined A/D converter [J]. J4, 2016, 43(1): 162-166+172.
[7]	ZHANG Maosen;QIU Zhiliang;GAO Ya;LI Jun. Reverse dispatching scheme for satellite Clos-network switches [J]. J4, 2013, 40(4): 96-101.
[8]	YUAN Bo;WANG Binqiang;WANG Zhiming. Green IP lookup architecture and algorithm based on the parallel multi-pipeline [J]. J4, 2012, 39(2): 145-152+167.
[9]	LI Xiaojuan;YANG Yintang. Offset cancellation preamplifier for pipelined folding A/D converter [J]. J4, 2012, 39(2): 95-100+174.
[10]	XIONG Herui；HAO Xuefei；HU Guorong. Low-cost hardware optimization design for high-speed GMC demodulation [J]. J4, 2011, 38(3): 169-174.
[11]	CHANG Hong;ZHAO Guo-qing;NIU Xin-liang. Efficient wideband digital channelized receiver design [J]. J4, 2010, 37(3): 464-468.
[12]	ZHANG Jing-bo1;DAI Xian-ying2;ZHANG He-ming2;HU Hui-yong1;JIA Da-zhong1. Area-efficient high-speed VLSI design of the RS(255,239) decoder [J]. J4, 2008, 35(1): 116-120.
[13]	LIU Jin;JI Hong-bing. Detection method for small targets in the IR image based on the variable weighted pipeline filter [J]. J4, 2007, 34(5): 743-747.

Design of the transcendental function computing unit of the computer vision array processor

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 13

Metrics

Comments

Recommended 10